iiinova — where your digital self keeps evolving

Louis Lippens @louislippens.be · 10/10/2025

The short answer: I apply UWLS via {fixest} and then avg_predictions(). Outcomes are CATEs in the form of log risk ratios. Regressors are study variables. Looks something like the code attached. (wlsmra() is a custom function that builds on fixest::feols().)

120

Louis Lippens @louislippens.be · 09/10/2025

For those curious, the first applicant, on average, receives 35% (95%CI = [−42%, −26%]) fewer positive responses, while the latter applicant receives 18% (95%CI = [−27%, −7%]) fewer positive responses compared to a plausible control group in that market.

110

Louis Lippens @louislippens.be · 09/10/2025

I can virtually "place" profiles in the labour market, such as a Middle Eastern jobseeker looking for a Manager role in Europe over the past 3 years, and compare their hiring penalty with that of a Black applicant seeking a sales role in the US during the same period, all else equal.

100

Louis Lippens @louislippens.be · 09/10/2025

I've been tinkering with a -finally finished- metadataset on hiring discrimination, representing roughly 1.4 million fictitious applications, and the power of contemporary meta-regression methods combined with tools such as {marginaleffects} really struck me.

100

Louis Lippens @louislippens.be · 22/09/2025

Quite funny conclusion given Boren’s “intelligence is what the test tests” (sic) take on intelligence in 1923, implicitly referring to the common underlying g factor. Appears these language model intelligence tests behave similarly.

010

Louis Lippens @louislippens.be · 19/06/2025

Glad to have been part of this stimulating workshop. Thanks to @vatsalecon.bsky.social, @sanchariroy.bsky.social, Javier García-Brazales, Sonia Oreffice, and others at @exeter.ac.uk for hosting. A draft paper on our research into the cyclicality of hiring discrimination should be available soon.

040

Louis Lippens @louislippens.be · 18/05/2025

I expected exactly what you expected. Not sure whether I used this in any of my code before, but seems like normal behaviour to me.

010

Louis Lippens @louislippens.be · 08/05/2025

Flemish professors working on US-linked projects recently received a questionnaire from the US embassy in Belgium surveying them on university diversity policies. Guess we're going to have to charge a 300% ‘nosy-survey’ tariff now. #econsky #academicsky www.vrt.be/vrtnws/en/20...

vrt.be

US embassy questions Flemish universities on diversity policy | VRT NWS: news

The American embassy has sent a questionnaire to Flemish universities about their diversity policies, Education Minister Zuhal Demir has confirmed.

0101

Louis Lippens @louislippens.be · 04/03/2025

We also plead that policymaking supports research that - evaluates under-researched types of discrimination; - provides broader insights into discrimination mechanisms; - pilot tests the efficacy of policy interventions.

100

Louis Lippens @louislippens.be · 04/03/2025

- ethnic discrimination varies by origin and is highest for MENA candidates; - the past decades have seen little reduction in hiring discrimination; - research increasingly focuses on identifying the mechanisms that may explain discrimination, but no conclusive view has emerged.

100

Louis Lippens @louislippens.be · 04/03/2025

Other insights are: - hiring discrimination based on gender appears mainly in occupations dominated by a specific gender; - age discrimination in hiring is substantial and under-researched in many countries; - age discrimination is lower in the US than in Europe;

100

Louis Lippens @louislippens.be · 04/03/2025

This insight is incompatible with policies focusing exclusively on one or a few vulnerable groups. Broad diversity policies, prioritising targeting those most disadvantaged, are needed.

100

Louis Lippens @louislippens.be · 04/03/2025

Our key insight is that many groups face hiring penalties. These penalties are highest for people with a disability, less physically attractive people, older people, and people of a minority race, ethnicity or national origin, respectively.

100

Louis Lippens @louislippens.be · 04/03/2025

Last week, @iza.org World of Labor published our policy article on hiring discrimination across vulnerable groups. In this article, we summarise insights from meta-research on the issue.

Figure 1 from the IZA World of Labor policy article displaying hiring discrimination estimates for the publication period 2005 until 2020. The graph shows differences in employer callbacks for various vulnerable groups compared to majority reference groups. The x-axis represents the percentage difference in callbacks. Negative values indicate discrimination (fewer callbacks for the vulnerable group). Each group is represented by a square (point estimate) and a ribbon (95% confidence interval). People with disabilities are discriminated against most, followed by less physically attractive people, older people, lesbian women and gay men, and people of a minority race, ethnicity, or national origin.

1103

Louis Lippens @louislippens.be · 13/02/2025

I've learned not to overinterpret them (by eye-balling). You should be best off using wviechtb.github.io/metafor/refe..., conducting sensitivity analyses with wviechtb.github.io/metafor/refe..., or immediately correcting for various forms of publication bias.

220

Louis Lippens @louislippens.be · 17/01/2025

We are also looking for a postdoc (90% research, 10% teaching). Application deadline approaching fast (21 January 2025).

jobs.ugent.be

Post-doctoral assistant department of Economics

000

Louis Lippens @louislippens.be · 17/01/2025

We have at least one open PhD position in our Labour Economics and Welfare research area (90% research, 10% teaching). Feel free to reach out for more details. Apply until 18 February 2025. #EconSky

120

Louis Lippens @louislippens.be · 20/12/2024

Actually didn't know of this package yet. Just tested out the functions. Seems extremely useful.

010

Louis Lippens @louislippens.be · 19/12/2024

I’ve been recently experiencing issues with modelsummary() not displaying tables in the Viewer pane, too. Must be RStudio then.

110

Louis Lippens @louislippens.be · 18/09/2024

WFH creates opportunities for people with a physical disability, who might otherwise not have been able to work full-time.

0102

Louis Lippens @louislippens.be · 10/09/2024

Prof. Attila Lindner briefly presented this at #EALE2024 along with some key insights that, at the margin, minimum wages are primarily passed through to consumers and improve firm efficiency. Also interesting to see meta-science increasingly permeating economics.

030

Reposted by Louis Lippens

Aaron Sojourner @aaronsojourner.org · 06/01/2024

Black Americans' employment rate exceeded (narrowly) white Americans' rate in Dec 2023, only the 2nd time in 52 years of data This graph shows the ratio of Black to white Americans' rates, with Black Americans' rate stably about 5 to 10 percent lower than whites' rate, until recently.

1199

Reposted by Louis Lippens

Aaron Sojourner @aaronsojourner.org · 21/11/2023

When a minimum wage increases: "Racial inequality decreases because firms disproportionately reduce callbacks to lower-quality white applicants who benefited from discrimination under lower minimum wages." research.upjohn.org/up_workingpa...

717071

Louis Lippens @louislippens.be · 14/11/2023

Really exciting and interesting work on labour market competition and its diminishing effects on wage inequality.

000

Reposted by Louis Lippens

Jordan Axt @jordanaxt.bsky.social · 30/10/2023

New article in Nature Human Behavior co-led by Aaron Nichols! In a Registered Report, we ran a field study to test whether images of organizational diversity impact the quality and quantity of applicants from majority and minority groups. www.nature.com/articles/s41...

14529

Reposted by Louis Lippens

Arin Dube @arindube.bsky.social · 10/10/2023

Good piece by @ryanlcooper.com on the importance of full employment - both for ensuring people are able to find jobs, and for helping improve the quality of those jobs.

14315

Reposted by Louis Lippens

Carl T. Bergstrom @carlbergstrom.com · 08/10/2023

I wanted to consolidate a few thoughts on google, misinformation, large language models, enshittification, and the fate of the web as we know it. It started when @carlzimmer.bsky.social shared this remarkable example of Google being fooled by machine-generated bullshit online. 1/n

16680318

Louis Lippens @louislippens.be · 05/10/2023

If you want to verify that your bsky account is effectively yours and you own a custom domain, then I recommend you follow the steps in the blog post below. (The same applies if you just want a custom handle, like I did, of course 😀.)

blueskyweb.xyz

How to set your domain as your handle

Using a domain as your handle helps with account identity, verification, and portability. Here's how to set your domain as your handle.

020

Louis Lippens @louislippens.be · 03/10/2023

Transposing the audit approach to ChatGPT, I find ChatGPT displays ethnic (but little gender) bias during CV screening, influenced by name cues and prompt language. The bias is substantial but generally less than human recruiters (cf. meta-analysis). Users should be wary of ChatGPT's adverse impact.

scholar.google.com

‪Computer says 'no': Exploring systemic hiring bias in ChatGPT using an audit approach‬

‪L Lippens‬, ‪arXiv, 2023‬

000

Louis Lippens @louislippens.be · 03/10/2023

In a correspondence audit study, we find evidence of hiring discrimination in Flanders (BE). Contextualising the results, non-Flemish applicants face little discrimination in non-profit or large organisations. There is partial support for less discrimination in low-contact and 'bottleneck' jobs.

sciencedirect.com

Understanding ethnic hiring discrimination:A contextual analysis of experimental evidence

Previous research has demonstrated that context matters in understanding unequal treatment in hiring—for example, some studies have illustrated that h…

101

Louis Lippens @louislippens.be · 03/10/2023

In our meta-analysis on hiring discrimination (2005-2020), we show discrimination is at least as severe for disability, age, and attractiveness as for ethnicity. Older candidates face more discrimination in Europe than in the US. Last, there is no consistent change in discrimination over time.

sciencedirect.com

The state of hiring discrimination: A meta-analysis of (almost) all recent correspondence experiment...

Notwithstanding the improved integration of various minority groups in the workforce, unequal treatment in hiring still hinders many individuals’ acce…

100

Louis Lippens @louislippens.be · 03/10/2023

Introduction! I'm a postdoc at Ghent University with an MSc in org. psychology and a joint PhD in economics & sociology. My research focuses mainly on work and the labour market and, more specifically, labour market discrimination. I highlight some recent research below.

louislippens.be

Louis Lippens

Louis Lippens, FWO postdoctoral researcher at Ghent University

130